Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tom-r-main-go
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/go
What's inside
- Skill name
go- Description
- Implement, review, debug, test, migrate, and optimize Go. Use for Go code, modules, and workspaces with the selected toolchain and repository build contract.
- License
- MIT
- Instructions
- 158 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (13)
- SKILL.md
- openai.yaml · agents/
- go-concurrency-context-memory.md · references/
- go-design-packages-errors.md · references/
- go-modules-toolchains-builds.md · references/
- go-performance-profiling.md · references/
- go-testing-fuzzing.md · references/
- go-unsafe-cgo-platforms.md · references/
- go-version-migrations.md · references/
- go-gates.sh · scripts/
- go_gates.py · scripts/
- evaluations.json · tests/
- test_go_gates.py · tests/
SKILL.md (first lines)
# Go Resolve `GO_SKILL_DIR` to the absolute directory containing this loaded `SKILL.md`. Run its scripts from the target repository root. Work from the repository's actual Go contract. The selected toolchain, active workspace, build driver, generated-code policy, target matrix, nearby code, and diagnostics outrank remembered APIs and generic style rules. ## Workflow ### 1. Establish the build contract Inspect before editing or running broad commands: ```sh git rev-parse --show-toplevel GOTOOLCHAIN=local go version GOTOOLCHAIN=local go env GOVERSION GOROOT GOMOD GOWORK GOOS GOARCH CGO_ENABLED GOEXPERIMENT rg -n '^(go|toolchain|module|use|replace|exclude|retract)[[:space:](]' -g 'go.mod' -g 'go.work' . rg -n '^//go:build|^//go:generate' -g '*.go' . ``` Read relevant `AGENTS.md` and contributor guidance, then inspect `go.mod`, `go.work`, `.go-version`, build scripts, lint configuration, generation rules, and CI. Determine: - module and workspace scope; - minimum, preferred, and CI Go versions; - the repository's focused test and verification commands; - build tags, GOOS/GOARCH, CGO, experiments, and privileged requirements; - generated or vendored artifacts and their supported update procedure. Keep these distinctions explicit: - A `go` directive sets a minimum toolchain and package language version; a `toolchain` directive names a preferred toolchain. `.go-version`, CI, and containers may select stricter development or release versions. - `GOTOOLCHAIN=auto` may download a toolchain. Use `GOTOOLCHAIN=local` for discovery until network access is permitted, and use `go list -m` to force a module/workspace compatibility check. - `GOWORK` is directory-sensitive and may include modules outside the repository. Do not edit or test external modules unless they are in scope. - Make, Task, Just, Mage, Bazel, repository scripts, and the Go source tree's own scripts may encode tags, generation, tools, and target selection. Inspect recipes before running them; a benign target name does not prove it is read-only. - Do not run `go mod tidy`, `go work sync`, `go generate`, `go fix`, vendoring, code generation, tool installation, or formatter write mode without scope and mutation authority. For module resolution, toolchains, workspaces, dependencies, build tags, and generators, read [references/go-modules-toolchains-builds.md](references/go-modules-toolchains-builds.md). ### 2. Load only the relevant guidance - Package/API design, interfaces, zero values, ownership, generics, and errors: [references/go-design-packages-errors.md](references/go-design-packages-errors.md) - Context, goroutine lifecycle, channels, locks, atomics, the memory model, race testing, and `testing/synctest`: [references/go-concurrency-context-memory.md](references/go-concurrency-context-memory.md) - Regression tests, subtests, parallelism, integration tests, fuzzing, coverage, caching, and flakes: [references/go-testing-fuzzing.md](references/go-testing-fuzzing.md) - Unsafe pointers, CGO, ABI, cross-compilation, OS/architecture behavior, eBPF, and privileged testing: [references/go-unsafe-cgo-platforms.md](references/go-unsafe-cgo-platforms.md) - Benchmarks, `benchstat`, pprof, trace, allocations, GC, and PGO: [references/go-performance-profiling.md](references/go-performance-profiling.md) - Go-version changes and modernization: [references/go-version-migrations.md](references/go-version-migrations.md) Open only the references needed for the task. Verify version-gated claims against the selected toolchain's documentation, release notes, and source. Effective Go is useful for core idioms, but it does not cover modules, generics, or all newer library and tooling behavior. ### 3. Make the narrow change - Read the relevant implementation, tests, callers, interfaces, and recent history. Search all consumers before changing public or shared behavior. - For a bug, first add or identify a focused regression test and observe the failure when reproducible; then implement the smallest correction and observe the test pass. State when the original failure cannot be reproduced locally. - Do not bundle dependency updates, modernization, renames, or cleanup with an unrelated fix. - Use `gopls` for semantic navigation, diagnostics, and refactors when available. Prefer compiler, analyzer, race, fuzz, benchmark, or repository evidence to model-only reasoning. - Comments should preserve contracts, invariants, ownership, cancellation, compatibility constraints, and non-obvious causality—not narrate syntax. - Keep independently correct changes reviewable. Each logical commit should compile and pass its relevant gates unless an explicitly reviewed failing regression-test commit precedes the fix. At boundaries, make these decisions explicit: - who may mutate, retain, copy, concurrently access, close, or reuse values and resources; - whether zero values are useful or constructors enforce required invariants; - whether errors remain inspectable through wrapping or are translated at the boundary; - who owns each goroutine and channel, how work is bounded, how cancellation is observed, and how completion is joined; - which exported behavior, error identity, wire format, CLI output, metric, or ordering property is a compatibility commitment. ### 4. Validate in a feedback loop Use the repository's narrowest applicable validation command after inspecting its recipe. For ordinary module-native repositories without a custom driver, run the bundled helper from the target package or module: ```sh "$GO_SKILL_DIR/scripts/go-gates.sh" ``` The helper requires POSIX `sh`, Python 3, Git, `go`, and `gofmt`; a configured `golangci-lint` is optional but must already be installed. It defaults to no
From Tom-R-Main/siftable-skills, MIT.
More from Tom-R-Main/siftable-skills
- 0.592score
pgvector-postgres
Tom-R-Main
Design, review, migrate, measure, or debug PostgreSQL vector retrieval with pgvector.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
paper-design
Tom-R-Main
Create, inspect, edit, import, export, and hand off product or visual designs through Paper and its MCP server.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
grok-guide
Tom-R-Main
Use Grok 4.5 as an explicit strategic control plane above Codex for plan, replan, and completion-audit lifecycles.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
plan
siftable
Produce a visual, grounded plan for an objective.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
filesystem-lifecycle
Tom-R-Main
Audit, classify, reclaim, and prevent regrowth of local filesystem cruft and agent-workspace storage.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
footwork-tools
Tom-R-Main
Equip an agent with observation and action tools for browser UI, native Mac apps, terminals/services, and saved artifacts.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
opengl-c-graphics
Tom-R-Main
Build, debug, review, and optimize core-profile OpenGL in C.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
c-systems-programming
Tom-R-Main
Implement, debug, and review C systems software.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
css
Tom-R-Main
Implement, debug, and review CSS and Tailwind styling.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
mermaid
siftable
Create Mermaid diagrams and render them through an available host renderer.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
cloud-environment-runtime
Tom-R-Main
Establish the selected cloud task's execution, network, and credential context before using cloud tools.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
generating-design-references
Tom-R-Main
Generate and critique a design-reference image when no existing visual precedent fits.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 12, 2026 (16 days ago)
- Last release
- Aug 14, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Tom-R-Main/siftable-skills
- Website
- siftable.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Tom-R-Main
- 0.592score
pgvector-postgres
Tom-R-Main
Design, review, migrate, measure, or debug PostgreSQL vector retrieval with pgvector.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
footwork-tools
Tom-R-Main
Equip an agent with observation and action tools for browser UI, native Mac apps, terminals/services, and saved artifacts.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
grok-guide
Tom-R-Main
Use Grok 4.5 as an explicit strategic control plane above Codex for plan, replan, and completion-audit lifecycles.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
paper-design
Tom-R-Main
Create, inspect, edit, import, export, and hand off product or visual designs through Paper and its MCP server.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
filesystem-lifecycle
Tom-R-Main
Audit, classify, reclaim, and prevent regrowth of local filesystem cruft and agent-workspace storage.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
css
Tom-R-Main
Implement, debug, and review CSS and Tailwind styling.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
go skill. Agent Mart. https://agentmart.dev/skills/tom-r-main-go (last updated 2026-10-24)